© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16735
    Prev
    Next
    INDEX
    Explanations

    file size units (MB, GB, Meg)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    éĶµ
    -0.10
    иÑĪ
    -0.10
    è¡®
    -0.10
    çļĦåĬªåĬĽ
    -0.10
    æł¸å¿ĥåĮº
    -0.09
    åĺ´éĩĮ
    -0.09
    adders
    -0.09
    å¾Ĺ天
    -0.09
    åĿ¡
    -0.09
    çĩİ
    -0.09
    POSITIVE LOGITS
    容éĩı
    0.12
    æľīå¤ļ大
    0.10
    Size
    0.10
    avern
    0.09
    é¾
    0.09
     size
    0.09
     Sizes
    0.09
     sizes
    0.09
    ä½ĵ积
    0.09
    太大
    0.08
    Activations Density 0.120%

    No Known Activations